http://www.genedenovo.com/news/584.html
https://new.qq.com/omn/20190125/20190125B1238Z.html
https://www.cnblogs.com/xiangshancuizhu/archive/2012/03/15/2397508.html
PCA
it is to explain a set of variables by linear combination of variable variance - covariance structure. PCA is used to reduce the dimension.
With the main reason for the PCA:
Data Compression:. PCA is typically used to compress the original message contains a large amount of data to a smaller set of new composite variables or dimensions, while doing little information loss.
Interpretation.
-
PCA can be used to discover important features of a large data set. It often reveals relationships that were previously unsuspected, thereby allowing interpretations of the data that may not ordinarily result from examination of the data. PCA is typically used as an intermediate step in data analysis when the number of input variables is otherwise too large to perform useful analysis.
-
PCA can find important feature of large data sets. It is often found hidden relationship. PCA data analysis is usually an intermediate step, when the input becomes useful for the analysis is too large.
Origin PCA provides the following functions:
- Descriptive Statistics Descriptive Statistics
- Correlation Matrix correlation matrix
- Eigenvalues of the Correlation Matrix correlation matrix eigenvalues
- Extracted Eigenvectors extracted feature vectors
- Scores for each observation value observed for each value of
- Plots plot
- Scree Plot
- Loading Plot
- BiPlot